PoliticalSpeech2 / last-checkpoint /trainer_state.json
MarkelFe's picture
Training in progress, step 350000
a3b0e88
raw
history blame
92.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 8.286769580452695,
"global_step": 350000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 3.913400890235818e-05,
"loss": 3.2516,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 3.907099788490072e-05,
"loss": 3.2746,
"step": 500
},
{
"epoch": 0.02,
"learning_rate": 3.900786059285918e-05,
"loss": 3.2966,
"step": 1000
},
{
"epoch": 0.04,
"learning_rate": 3.894472330081763e-05,
"loss": 3.2988,
"step": 1500
},
{
"epoch": 0.05,
"learning_rate": 3.888158600877609e-05,
"loss": 3.2782,
"step": 2000
},
{
"epoch": 0.06,
"learning_rate": 3.8818448716734545e-05,
"loss": 3.2631,
"step": 2500
},
{
"epoch": 0.07,
"learning_rate": 3.8755311424693e-05,
"loss": 3.2792,
"step": 3000
},
{
"epoch": 0.08,
"learning_rate": 3.8692174132651456e-05,
"loss": 3.2848,
"step": 3500
},
{
"epoch": 0.09,
"learning_rate": 3.862903684060991e-05,
"loss": 3.2699,
"step": 4000
},
{
"epoch": 0.11,
"learning_rate": 3.8565899548568366e-05,
"loss": 3.2634,
"step": 4500
},
{
"epoch": 0.12,
"learning_rate": 3.8502762256526824e-05,
"loss": 3.276,
"step": 5000
},
{
"epoch": 0.13,
"learning_rate": 3.8439624964485276e-05,
"loss": 3.2431,
"step": 5500
},
{
"epoch": 0.14,
"learning_rate": 3.8376487672443735e-05,
"loss": 3.261,
"step": 6000
},
{
"epoch": 0.15,
"learning_rate": 3.8313350380402186e-05,
"loss": 3.2711,
"step": 6500
},
{
"epoch": 0.17,
"learning_rate": 3.8250213088360645e-05,
"loss": 3.2567,
"step": 7000
},
{
"epoch": 0.18,
"learning_rate": 3.8187075796319097e-05,
"loss": 3.2721,
"step": 7500
},
{
"epoch": 0.19,
"learning_rate": 3.8123938504277555e-05,
"loss": 3.2305,
"step": 8000
},
{
"epoch": 0.2,
"learning_rate": 3.806080121223601e-05,
"loss": 3.2749,
"step": 8500
},
{
"epoch": 0.21,
"learning_rate": 3.7997663920194465e-05,
"loss": 3.245,
"step": 9000
},
{
"epoch": 0.22,
"learning_rate": 3.7934526628152924e-05,
"loss": 3.251,
"step": 9500
},
{
"epoch": 0.24,
"learning_rate": 3.7871389336111375e-05,
"loss": 3.2401,
"step": 10000
},
{
"epoch": 0.24,
"eval_loss": 3.248208999633789,
"eval_runtime": 113.4703,
"eval_samples_per_second": 165.435,
"eval_steps_per_second": 20.684,
"step": 10000
},
{
"epoch": 0.25,
"learning_rate": 3.7808252044069834e-05,
"loss": 3.2605,
"step": 10500
},
{
"epoch": 0.26,
"learning_rate": 3.7745114752028286e-05,
"loss": 3.2545,
"step": 11000
},
{
"epoch": 0.27,
"learning_rate": 3.7681977459986744e-05,
"loss": 3.2566,
"step": 11500
},
{
"epoch": 0.28,
"learning_rate": 3.76188401679452e-05,
"loss": 3.2435,
"step": 12000
},
{
"epoch": 0.3,
"learning_rate": 3.7555702875903654e-05,
"loss": 3.2426,
"step": 12500
},
{
"epoch": 0.31,
"learning_rate": 3.749256558386211e-05,
"loss": 3.2473,
"step": 13000
},
{
"epoch": 0.32,
"learning_rate": 3.742942829182057e-05,
"loss": 3.2466,
"step": 13500
},
{
"epoch": 0.33,
"learning_rate": 3.736629099977902e-05,
"loss": 3.2552,
"step": 14000
},
{
"epoch": 0.34,
"learning_rate": 3.7303153707737475e-05,
"loss": 3.2523,
"step": 14500
},
{
"epoch": 0.36,
"learning_rate": 3.724001641569593e-05,
"loss": 3.239,
"step": 15000
},
{
"epoch": 0.37,
"learning_rate": 3.7176879123654385e-05,
"loss": 3.2455,
"step": 15500
},
{
"epoch": 0.38,
"learning_rate": 3.7113741831612843e-05,
"loss": 3.2408,
"step": 16000
},
{
"epoch": 0.39,
"learning_rate": 3.70506045395713e-05,
"loss": 3.2481,
"step": 16500
},
{
"epoch": 0.4,
"learning_rate": 3.6987467247529754e-05,
"loss": 3.2284,
"step": 17000
},
{
"epoch": 0.41,
"learning_rate": 3.692432995548821e-05,
"loss": 3.2339,
"step": 17500
},
{
"epoch": 0.43,
"learning_rate": 3.686119266344667e-05,
"loss": 3.2251,
"step": 18000
},
{
"epoch": 0.44,
"learning_rate": 3.679805537140512e-05,
"loss": 3.2356,
"step": 18500
},
{
"epoch": 0.45,
"learning_rate": 3.673491807936358e-05,
"loss": 3.2189,
"step": 19000
},
{
"epoch": 0.46,
"learning_rate": 3.667178078732203e-05,
"loss": 3.2285,
"step": 19500
},
{
"epoch": 0.47,
"learning_rate": 3.660864349528049e-05,
"loss": 3.2312,
"step": 20000
},
{
"epoch": 0.47,
"eval_loss": 3.2111425399780273,
"eval_runtime": 113.0759,
"eval_samples_per_second": 166.012,
"eval_steps_per_second": 20.756,
"step": 20000
},
{
"epoch": 0.49,
"learning_rate": 3.654550620323895e-05,
"loss": 3.2209,
"step": 20500
},
{
"epoch": 0.5,
"learning_rate": 3.64823689111974e-05,
"loss": 3.241,
"step": 21000
},
{
"epoch": 0.51,
"learning_rate": 3.641923161915586e-05,
"loss": 3.2175,
"step": 21500
},
{
"epoch": 0.52,
"learning_rate": 3.635609432711432e-05,
"loss": 3.2178,
"step": 22000
},
{
"epoch": 0.53,
"learning_rate": 3.629295703507277e-05,
"loss": 3.2193,
"step": 22500
},
{
"epoch": 0.54,
"learning_rate": 3.622981974303122e-05,
"loss": 3.2356,
"step": 23000
},
{
"epoch": 0.56,
"learning_rate": 3.616668245098968e-05,
"loss": 3.2214,
"step": 23500
},
{
"epoch": 0.57,
"learning_rate": 3.610354515894813e-05,
"loss": 3.2206,
"step": 24000
},
{
"epoch": 0.58,
"learning_rate": 3.604040786690659e-05,
"loss": 3.2182,
"step": 24500
},
{
"epoch": 0.59,
"learning_rate": 3.597727057486505e-05,
"loss": 3.2142,
"step": 25000
},
{
"epoch": 0.6,
"learning_rate": 3.59141332828235e-05,
"loss": 3.2211,
"step": 25500
},
{
"epoch": 0.62,
"learning_rate": 3.585099599078196e-05,
"loss": 3.2168,
"step": 26000
},
{
"epoch": 0.63,
"learning_rate": 3.578785869874041e-05,
"loss": 3.2236,
"step": 26500
},
{
"epoch": 0.64,
"learning_rate": 3.572472140669887e-05,
"loss": 3.2165,
"step": 27000
},
{
"epoch": 0.65,
"learning_rate": 3.566158411465733e-05,
"loss": 3.1985,
"step": 27500
},
{
"epoch": 0.66,
"learning_rate": 3.559844682261578e-05,
"loss": 3.2057,
"step": 28000
},
{
"epoch": 0.67,
"learning_rate": 3.553530953057424e-05,
"loss": 3.1979,
"step": 28500
},
{
"epoch": 0.69,
"learning_rate": 3.5472172238532697e-05,
"loss": 3.2124,
"step": 29000
},
{
"epoch": 0.7,
"learning_rate": 3.540903494649115e-05,
"loss": 3.2094,
"step": 29500
},
{
"epoch": 0.71,
"learning_rate": 3.534589765444961e-05,
"loss": 3.2106,
"step": 30000
},
{
"epoch": 0.71,
"eval_loss": 3.183478355407715,
"eval_runtime": 113.0965,
"eval_samples_per_second": 165.982,
"eval_steps_per_second": 20.752,
"step": 30000
},
{
"epoch": 0.72,
"learning_rate": 3.528276036240806e-05,
"loss": 3.2187,
"step": 30500
},
{
"epoch": 0.73,
"learning_rate": 3.521962307036651e-05,
"loss": 3.2015,
"step": 31000
},
{
"epoch": 0.75,
"learning_rate": 3.515648577832497e-05,
"loss": 3.2153,
"step": 31500
},
{
"epoch": 0.76,
"learning_rate": 3.509334848628343e-05,
"loss": 3.2242,
"step": 32000
},
{
"epoch": 0.77,
"learning_rate": 3.503021119424188e-05,
"loss": 3.2025,
"step": 32500
},
{
"epoch": 0.78,
"learning_rate": 3.496707390220034e-05,
"loss": 3.2164,
"step": 33000
},
{
"epoch": 0.79,
"learning_rate": 3.4903936610158796e-05,
"loss": 3.1862,
"step": 33500
},
{
"epoch": 0.81,
"learning_rate": 3.484079931811725e-05,
"loss": 3.207,
"step": 34000
},
{
"epoch": 0.82,
"learning_rate": 3.4777662026075706e-05,
"loss": 3.1953,
"step": 34500
},
{
"epoch": 0.83,
"learning_rate": 3.471452473403416e-05,
"loss": 3.1788,
"step": 35000
},
{
"epoch": 0.84,
"learning_rate": 3.4651387441992616e-05,
"loss": 3.1987,
"step": 35500
},
{
"epoch": 0.85,
"learning_rate": 3.4588250149951075e-05,
"loss": 3.1914,
"step": 36000
},
{
"epoch": 0.86,
"learning_rate": 3.4525112857909527e-05,
"loss": 3.2037,
"step": 36500
},
{
"epoch": 0.88,
"learning_rate": 3.4461975565867985e-05,
"loss": 3.1951,
"step": 37000
},
{
"epoch": 0.89,
"learning_rate": 3.4398838273826444e-05,
"loss": 3.1909,
"step": 37500
},
{
"epoch": 0.9,
"learning_rate": 3.433570098178489e-05,
"loss": 3.2012,
"step": 38000
},
{
"epoch": 0.91,
"learning_rate": 3.427256368974335e-05,
"loss": 3.2092,
"step": 38500
},
{
"epoch": 0.92,
"learning_rate": 3.4209426397701805e-05,
"loss": 3.2108,
"step": 39000
},
{
"epoch": 0.94,
"learning_rate": 3.414628910566026e-05,
"loss": 3.1818,
"step": 39500
},
{
"epoch": 0.95,
"learning_rate": 3.4083151813618716e-05,
"loss": 3.2072,
"step": 40000
},
{
"epoch": 0.95,
"eval_loss": 3.1675474643707275,
"eval_runtime": 113.0729,
"eval_samples_per_second": 166.017,
"eval_steps_per_second": 20.757,
"step": 40000
},
{
"epoch": 0.96,
"learning_rate": 3.4020014521577174e-05,
"loss": 3.2013,
"step": 40500
},
{
"epoch": 0.97,
"learning_rate": 3.3956877229535626e-05,
"loss": 3.1909,
"step": 41000
},
{
"epoch": 0.98,
"learning_rate": 3.3893739937494084e-05,
"loss": 3.1857,
"step": 41500
},
{
"epoch": 0.99,
"learning_rate": 3.3830602645452536e-05,
"loss": 3.1904,
"step": 42000
},
{
"epoch": 1.01,
"learning_rate": 3.3767465353410995e-05,
"loss": 3.0815,
"step": 42500
},
{
"epoch": 1.02,
"learning_rate": 3.370432806136945e-05,
"loss": 3.0012,
"step": 43000
},
{
"epoch": 1.03,
"learning_rate": 3.3641190769327905e-05,
"loss": 2.9995,
"step": 43500
},
{
"epoch": 1.04,
"learning_rate": 3.357805347728636e-05,
"loss": 3.0085,
"step": 44000
},
{
"epoch": 1.05,
"learning_rate": 3.351491618524482e-05,
"loss": 3.0499,
"step": 44500
},
{
"epoch": 1.07,
"learning_rate": 3.3451778893203274e-05,
"loss": 3.0286,
"step": 45000
},
{
"epoch": 1.08,
"learning_rate": 3.338864160116173e-05,
"loss": 3.0233,
"step": 45500
},
{
"epoch": 1.09,
"learning_rate": 3.3325504309120184e-05,
"loss": 3.0465,
"step": 46000
},
{
"epoch": 1.1,
"learning_rate": 3.3262367017078635e-05,
"loss": 3.0409,
"step": 46500
},
{
"epoch": 1.11,
"learning_rate": 3.3199229725037094e-05,
"loss": 3.0265,
"step": 47000
},
{
"epoch": 1.12,
"learning_rate": 3.313609243299555e-05,
"loss": 3.0177,
"step": 47500
},
{
"epoch": 1.14,
"learning_rate": 3.3072955140954004e-05,
"loss": 3.0255,
"step": 48000
},
{
"epoch": 1.15,
"learning_rate": 3.300981784891246e-05,
"loss": 3.0417,
"step": 48500
},
{
"epoch": 1.16,
"learning_rate": 3.294668055687092e-05,
"loss": 3.0222,
"step": 49000
},
{
"epoch": 1.17,
"learning_rate": 3.288354326482937e-05,
"loss": 3.0286,
"step": 49500
},
{
"epoch": 1.18,
"learning_rate": 3.282040597278783e-05,
"loss": 3.0283,
"step": 50000
},
{
"epoch": 1.18,
"eval_loss": 3.1600818634033203,
"eval_runtime": 113.1846,
"eval_samples_per_second": 165.853,
"eval_steps_per_second": 20.736,
"step": 50000
},
{
"epoch": 1.2,
"learning_rate": 3.275726868074628e-05,
"loss": 3.0453,
"step": 50500
},
{
"epoch": 1.21,
"learning_rate": 3.269413138870474e-05,
"loss": 3.014,
"step": 51000
},
{
"epoch": 1.22,
"learning_rate": 3.26309940966632e-05,
"loss": 3.0549,
"step": 51500
},
{
"epoch": 1.23,
"learning_rate": 3.256785680462165e-05,
"loss": 3.0268,
"step": 52000
},
{
"epoch": 1.24,
"learning_rate": 3.250471951258011e-05,
"loss": 3.0389,
"step": 52500
},
{
"epoch": 1.25,
"learning_rate": 3.244158222053857e-05,
"loss": 3.0315,
"step": 53000
},
{
"epoch": 1.27,
"learning_rate": 3.237844492849702e-05,
"loss": 3.0363,
"step": 53500
},
{
"epoch": 1.28,
"learning_rate": 3.231530763645547e-05,
"loss": 3.0291,
"step": 54000
},
{
"epoch": 1.29,
"learning_rate": 3.225217034441393e-05,
"loss": 3.0257,
"step": 54500
},
{
"epoch": 1.3,
"learning_rate": 3.218903305237238e-05,
"loss": 3.0457,
"step": 55000
},
{
"epoch": 1.31,
"learning_rate": 3.212589576033084e-05,
"loss": 3.0431,
"step": 55500
},
{
"epoch": 1.33,
"learning_rate": 3.20627584682893e-05,
"loss": 3.0591,
"step": 56000
},
{
"epoch": 1.34,
"learning_rate": 3.199962117624775e-05,
"loss": 3.0525,
"step": 56500
},
{
"epoch": 1.35,
"learning_rate": 3.193648388420621e-05,
"loss": 3.0479,
"step": 57000
},
{
"epoch": 1.36,
"learning_rate": 3.187334659216466e-05,
"loss": 3.019,
"step": 57500
},
{
"epoch": 1.37,
"learning_rate": 3.181020930012312e-05,
"loss": 3.0356,
"step": 58000
},
{
"epoch": 1.39,
"learning_rate": 3.174707200808158e-05,
"loss": 3.0549,
"step": 58500
},
{
"epoch": 1.4,
"learning_rate": 3.168393471604003e-05,
"loss": 3.0439,
"step": 59000
},
{
"epoch": 1.41,
"learning_rate": 3.162079742399849e-05,
"loss": 3.0491,
"step": 59500
},
{
"epoch": 1.42,
"learning_rate": 3.155766013195695e-05,
"loss": 3.0409,
"step": 60000
},
{
"epoch": 1.42,
"eval_loss": 3.1459972858428955,
"eval_runtime": 113.0693,
"eval_samples_per_second": 166.022,
"eval_steps_per_second": 20.757,
"step": 60000
},
{
"epoch": 1.43,
"learning_rate": 3.14945228399154e-05,
"loss": 3.0478,
"step": 60500
},
{
"epoch": 1.44,
"learning_rate": 3.143138554787386e-05,
"loss": 3.0372,
"step": 61000
},
{
"epoch": 1.46,
"learning_rate": 3.136824825583231e-05,
"loss": 3.0581,
"step": 61500
},
{
"epoch": 1.47,
"learning_rate": 3.130511096379076e-05,
"loss": 3.0544,
"step": 62000
},
{
"epoch": 1.48,
"learning_rate": 3.124197367174922e-05,
"loss": 3.0552,
"step": 62500
},
{
"epoch": 1.49,
"learning_rate": 3.117883637970768e-05,
"loss": 3.0614,
"step": 63000
},
{
"epoch": 1.5,
"learning_rate": 3.111569908766613e-05,
"loss": 3.0444,
"step": 63500
},
{
"epoch": 1.52,
"learning_rate": 3.105256179562459e-05,
"loss": 3.0622,
"step": 64000
},
{
"epoch": 1.53,
"learning_rate": 3.0989424503583046e-05,
"loss": 3.0649,
"step": 64500
},
{
"epoch": 1.54,
"learning_rate": 3.09262872115415e-05,
"loss": 3.0327,
"step": 65000
},
{
"epoch": 1.55,
"learning_rate": 3.086314991949996e-05,
"loss": 3.0226,
"step": 65500
},
{
"epoch": 1.56,
"learning_rate": 3.080001262745841e-05,
"loss": 3.0268,
"step": 66000
},
{
"epoch": 1.57,
"learning_rate": 3.073687533541687e-05,
"loss": 3.0442,
"step": 66500
},
{
"epoch": 1.59,
"learning_rate": 3.0673738043375325e-05,
"loss": 3.0545,
"step": 67000
},
{
"epoch": 1.6,
"learning_rate": 3.061060075133378e-05,
"loss": 3.0479,
"step": 67500
},
{
"epoch": 1.61,
"learning_rate": 3.0547463459292236e-05,
"loss": 3.0521,
"step": 68000
},
{
"epoch": 1.62,
"learning_rate": 3.048432616725069e-05,
"loss": 3.0666,
"step": 68500
},
{
"epoch": 1.63,
"learning_rate": 3.0421188875209146e-05,
"loss": 3.0512,
"step": 69000
},
{
"epoch": 1.65,
"learning_rate": 3.0358051583167604e-05,
"loss": 3.0455,
"step": 69500
},
{
"epoch": 1.66,
"learning_rate": 3.0294914291126053e-05,
"loss": 3.0549,
"step": 70000
},
{
"epoch": 1.66,
"eval_loss": 3.1334924697875977,
"eval_runtime": 113.1767,
"eval_samples_per_second": 165.865,
"eval_steps_per_second": 20.737,
"step": 70000
},
{
"epoch": 1.67,
"learning_rate": 3.023177699908451e-05,
"loss": 3.0289,
"step": 70500
},
{
"epoch": 1.68,
"learning_rate": 3.0168639707042966e-05,
"loss": 3.0267,
"step": 71000
},
{
"epoch": 1.69,
"learning_rate": 3.010550241500142e-05,
"loss": 3.0403,
"step": 71500
},
{
"epoch": 1.7,
"learning_rate": 3.0042365122959876e-05,
"loss": 3.0234,
"step": 72000
},
{
"epoch": 1.72,
"learning_rate": 2.9979227830918335e-05,
"loss": 3.0393,
"step": 72500
},
{
"epoch": 1.73,
"learning_rate": 2.991609053887679e-05,
"loss": 3.0527,
"step": 73000
},
{
"epoch": 1.74,
"learning_rate": 2.9852953246835245e-05,
"loss": 3.0477,
"step": 73500
},
{
"epoch": 1.75,
"learning_rate": 2.97898159547937e-05,
"loss": 3.0341,
"step": 74000
},
{
"epoch": 1.76,
"learning_rate": 2.972667866275216e-05,
"loss": 3.0533,
"step": 74500
},
{
"epoch": 1.78,
"learning_rate": 2.9663541370710614e-05,
"loss": 3.0478,
"step": 75000
},
{
"epoch": 1.79,
"learning_rate": 2.960040407866907e-05,
"loss": 3.0803,
"step": 75500
},
{
"epoch": 1.8,
"learning_rate": 2.9537266786627524e-05,
"loss": 3.0575,
"step": 76000
},
{
"epoch": 1.81,
"learning_rate": 2.9474129494585983e-05,
"loss": 3.0503,
"step": 76500
},
{
"epoch": 1.82,
"learning_rate": 2.9410992202544438e-05,
"loss": 3.0589,
"step": 77000
},
{
"epoch": 1.83,
"learning_rate": 2.9347854910502893e-05,
"loss": 3.0339,
"step": 77500
},
{
"epoch": 1.85,
"learning_rate": 2.9284717618461344e-05,
"loss": 3.0485,
"step": 78000
},
{
"epoch": 1.86,
"learning_rate": 2.92215803264198e-05,
"loss": 3.0359,
"step": 78500
},
{
"epoch": 1.87,
"learning_rate": 2.9158443034378258e-05,
"loss": 3.0268,
"step": 79000
},
{
"epoch": 1.88,
"learning_rate": 2.9095305742336713e-05,
"loss": 3.042,
"step": 79500
},
{
"epoch": 1.89,
"learning_rate": 2.9032168450295168e-05,
"loss": 3.0534,
"step": 80000
},
{
"epoch": 1.89,
"eval_loss": 3.1211836338043213,
"eval_runtime": 113.0858,
"eval_samples_per_second": 165.998,
"eval_steps_per_second": 20.754,
"step": 80000
},
{
"epoch": 1.91,
"learning_rate": 2.8969031158253623e-05,
"loss": 3.0544,
"step": 80500
},
{
"epoch": 1.92,
"learning_rate": 2.8905893866212082e-05,
"loss": 3.0379,
"step": 81000
},
{
"epoch": 1.93,
"learning_rate": 2.8842756574170537e-05,
"loss": 3.0446,
"step": 81500
},
{
"epoch": 1.94,
"learning_rate": 2.8779619282128992e-05,
"loss": 3.0499,
"step": 82000
},
{
"epoch": 1.95,
"learning_rate": 2.8716481990087447e-05,
"loss": 3.0582,
"step": 82500
},
{
"epoch": 1.97,
"learning_rate": 2.8653344698045906e-05,
"loss": 3.0423,
"step": 83000
},
{
"epoch": 1.98,
"learning_rate": 2.859020740600436e-05,
"loss": 3.0299,
"step": 83500
},
{
"epoch": 1.99,
"learning_rate": 2.8527070113962816e-05,
"loss": 3.0471,
"step": 84000
},
{
"epoch": 2.0,
"learning_rate": 2.846393282192127e-05,
"loss": 3.0438,
"step": 84500
},
{
"epoch": 2.01,
"learning_rate": 2.8400795529879726e-05,
"loss": 2.8724,
"step": 85000
},
{
"epoch": 2.02,
"learning_rate": 2.8337658237838178e-05,
"loss": 2.8515,
"step": 85500
},
{
"epoch": 2.04,
"learning_rate": 2.8274520945796636e-05,
"loss": 2.87,
"step": 86000
},
{
"epoch": 2.05,
"learning_rate": 2.821138365375509e-05,
"loss": 2.868,
"step": 86500
},
{
"epoch": 2.06,
"learning_rate": 2.8148246361713547e-05,
"loss": 2.861,
"step": 87000
},
{
"epoch": 2.07,
"learning_rate": 2.8085109069672e-05,
"loss": 2.8847,
"step": 87500
},
{
"epoch": 2.08,
"learning_rate": 2.802197177763046e-05,
"loss": 2.8808,
"step": 88000
},
{
"epoch": 2.1,
"learning_rate": 2.7958834485588915e-05,
"loss": 2.8786,
"step": 88500
},
{
"epoch": 2.11,
"learning_rate": 2.789569719354737e-05,
"loss": 2.8813,
"step": 89000
},
{
"epoch": 2.12,
"learning_rate": 2.7832559901505825e-05,
"loss": 2.8764,
"step": 89500
},
{
"epoch": 2.13,
"learning_rate": 2.7769422609464284e-05,
"loss": 2.8728,
"step": 90000
},
{
"epoch": 2.13,
"eval_loss": 3.1320364475250244,
"eval_runtime": 112.8722,
"eval_samples_per_second": 166.312,
"eval_steps_per_second": 20.793,
"step": 90000
},
{
"epoch": 2.14,
"learning_rate": 2.770628531742274e-05,
"loss": 2.8933,
"step": 90500
},
{
"epoch": 2.15,
"learning_rate": 2.7643148025381194e-05,
"loss": 2.8842,
"step": 91000
},
{
"epoch": 2.17,
"learning_rate": 2.758001073333965e-05,
"loss": 2.8859,
"step": 91500
},
{
"epoch": 2.18,
"learning_rate": 2.7516873441298108e-05,
"loss": 2.8765,
"step": 92000
},
{
"epoch": 2.19,
"learning_rate": 2.7453736149256563e-05,
"loss": 2.8814,
"step": 92500
},
{
"epoch": 2.2,
"learning_rate": 2.7390598857215018e-05,
"loss": 2.8964,
"step": 93000
},
{
"epoch": 2.21,
"learning_rate": 2.732746156517347e-05,
"loss": 2.9037,
"step": 93500
},
{
"epoch": 2.23,
"learning_rate": 2.7264324273131925e-05,
"loss": 2.8856,
"step": 94000
},
{
"epoch": 2.24,
"learning_rate": 2.7201186981090383e-05,
"loss": 2.8979,
"step": 94500
},
{
"epoch": 2.25,
"learning_rate": 2.713804968904884e-05,
"loss": 2.8945,
"step": 95000
},
{
"epoch": 2.26,
"learning_rate": 2.7074912397007294e-05,
"loss": 2.9037,
"step": 95500
},
{
"epoch": 2.27,
"learning_rate": 2.701177510496575e-05,
"loss": 2.9087,
"step": 96000
},
{
"epoch": 2.28,
"learning_rate": 2.6948637812924207e-05,
"loss": 2.905,
"step": 96500
},
{
"epoch": 2.3,
"learning_rate": 2.6885500520882662e-05,
"loss": 2.9209,
"step": 97000
},
{
"epoch": 2.31,
"learning_rate": 2.6822363228841117e-05,
"loss": 2.895,
"step": 97500
},
{
"epoch": 2.32,
"learning_rate": 2.6759225936799572e-05,
"loss": 2.8885,
"step": 98000
},
{
"epoch": 2.33,
"learning_rate": 2.6696088644758028e-05,
"loss": 2.9038,
"step": 98500
},
{
"epoch": 2.34,
"learning_rate": 2.6632951352716486e-05,
"loss": 2.9143,
"step": 99000
},
{
"epoch": 2.36,
"learning_rate": 2.656981406067494e-05,
"loss": 2.9099,
"step": 99500
},
{
"epoch": 2.37,
"learning_rate": 2.6506676768633396e-05,
"loss": 2.9092,
"step": 100000
},
{
"epoch": 2.37,
"eval_loss": 3.122859477996826,
"eval_runtime": 113.0124,
"eval_samples_per_second": 166.106,
"eval_steps_per_second": 20.768,
"step": 100000
},
{
"epoch": 2.38,
"learning_rate": 2.644353947659185e-05,
"loss": 2.766,
"step": 100500
},
{
"epoch": 2.39,
"learning_rate": 2.638040218455031e-05,
"loss": 2.7858,
"step": 101000
},
{
"epoch": 2.4,
"learning_rate": 2.631726489250876e-05,
"loss": 2.7735,
"step": 101500
},
{
"epoch": 2.42,
"learning_rate": 2.6254127600467217e-05,
"loss": 2.7908,
"step": 102000
},
{
"epoch": 2.43,
"learning_rate": 2.6190990308425672e-05,
"loss": 2.814,
"step": 102500
},
{
"epoch": 2.44,
"learning_rate": 2.6127853016384127e-05,
"loss": 2.7823,
"step": 103000
},
{
"epoch": 2.45,
"learning_rate": 2.6064715724342585e-05,
"loss": 2.7855,
"step": 103500
},
{
"epoch": 2.46,
"learning_rate": 2.600157843230104e-05,
"loss": 2.7984,
"step": 104000
},
{
"epoch": 2.47,
"learning_rate": 2.5938441140259496e-05,
"loss": 2.8117,
"step": 104500
},
{
"epoch": 2.49,
"learning_rate": 2.587530384821795e-05,
"loss": 2.8052,
"step": 105000
},
{
"epoch": 2.5,
"learning_rate": 2.581216655617641e-05,
"loss": 2.8137,
"step": 105500
},
{
"epoch": 2.51,
"learning_rate": 2.5749029264134864e-05,
"loss": 2.8106,
"step": 106000
},
{
"epoch": 2.52,
"learning_rate": 2.568589197209332e-05,
"loss": 2.796,
"step": 106500
},
{
"epoch": 2.53,
"learning_rate": 2.5622754680051775e-05,
"loss": 2.8181,
"step": 107000
},
{
"epoch": 2.55,
"learning_rate": 2.5559617388010233e-05,
"loss": 2.806,
"step": 107500
},
{
"epoch": 2.56,
"learning_rate": 2.5496480095968688e-05,
"loss": 2.8292,
"step": 108000
},
{
"epoch": 2.57,
"learning_rate": 2.5433342803927143e-05,
"loss": 2.8104,
"step": 108500
},
{
"epoch": 2.58,
"learning_rate": 2.53702055118856e-05,
"loss": 2.8292,
"step": 109000
},
{
"epoch": 2.59,
"learning_rate": 2.530706821984405e-05,
"loss": 2.8115,
"step": 109500
},
{
"epoch": 2.6,
"learning_rate": 2.524393092780251e-05,
"loss": 2.8272,
"step": 110000
},
{
"epoch": 2.6,
"eval_loss": 3.1270127296447754,
"eval_runtime": 113.6604,
"eval_samples_per_second": 165.159,
"eval_steps_per_second": 20.649,
"step": 110000
},
{
"epoch": 2.62,
"learning_rate": 2.5180793635760964e-05,
"loss": 2.842,
"step": 110500
},
{
"epoch": 2.63,
"learning_rate": 2.511765634371942e-05,
"loss": 2.8213,
"step": 111000
},
{
"epoch": 2.64,
"learning_rate": 2.5054519051677874e-05,
"loss": 2.8193,
"step": 111500
},
{
"epoch": 2.65,
"learning_rate": 2.499138175963633e-05,
"loss": 2.8396,
"step": 112000
},
{
"epoch": 2.66,
"learning_rate": 2.4928244467594787e-05,
"loss": 2.8274,
"step": 112500
},
{
"epoch": 2.68,
"learning_rate": 2.4865107175553243e-05,
"loss": 2.8153,
"step": 113000
},
{
"epoch": 2.69,
"learning_rate": 2.4801969883511698e-05,
"loss": 2.8443,
"step": 113500
},
{
"epoch": 2.7,
"learning_rate": 2.4738832591470153e-05,
"loss": 2.8377,
"step": 114000
},
{
"epoch": 2.71,
"learning_rate": 2.467569529942861e-05,
"loss": 2.8378,
"step": 114500
},
{
"epoch": 2.72,
"learning_rate": 2.4612558007387066e-05,
"loss": 2.8374,
"step": 115000
},
{
"epoch": 2.73,
"learning_rate": 2.454942071534552e-05,
"loss": 2.823,
"step": 115500
},
{
"epoch": 2.75,
"learning_rate": 2.4486283423303977e-05,
"loss": 2.8538,
"step": 116000
},
{
"epoch": 2.76,
"learning_rate": 2.4423146131262435e-05,
"loss": 2.8231,
"step": 116500
},
{
"epoch": 2.77,
"learning_rate": 2.436000883922089e-05,
"loss": 2.8326,
"step": 117000
},
{
"epoch": 2.78,
"learning_rate": 2.4296871547179342e-05,
"loss": 2.8421,
"step": 117500
},
{
"epoch": 2.79,
"learning_rate": 2.4233734255137797e-05,
"loss": 2.8478,
"step": 118000
},
{
"epoch": 2.81,
"learning_rate": 2.4170596963096252e-05,
"loss": 2.8496,
"step": 118500
},
{
"epoch": 2.82,
"learning_rate": 2.410745967105471e-05,
"loss": 2.846,
"step": 119000
},
{
"epoch": 2.83,
"learning_rate": 2.4044322379013166e-05,
"loss": 2.8532,
"step": 119500
},
{
"epoch": 2.84,
"learning_rate": 2.398118508697162e-05,
"loss": 2.8514,
"step": 120000
},
{
"epoch": 2.84,
"eval_loss": 3.121030807495117,
"eval_runtime": 113.6484,
"eval_samples_per_second": 165.176,
"eval_steps_per_second": 20.651,
"step": 120000
},
{
"epoch": 2.85,
"learning_rate": 2.3918047794930076e-05,
"loss": 2.8185,
"step": 120500
},
{
"epoch": 2.86,
"learning_rate": 2.3854910502888534e-05,
"loss": 2.8496,
"step": 121000
},
{
"epoch": 2.88,
"learning_rate": 2.379177321084699e-05,
"loss": 2.8448,
"step": 121500
},
{
"epoch": 2.89,
"learning_rate": 2.3728635918805445e-05,
"loss": 2.8327,
"step": 122000
},
{
"epoch": 2.9,
"learning_rate": 2.36654986267639e-05,
"loss": 2.8627,
"step": 122500
},
{
"epoch": 2.91,
"learning_rate": 2.3602361334722358e-05,
"loss": 2.83,
"step": 123000
},
{
"epoch": 2.92,
"learning_rate": 2.3539224042680813e-05,
"loss": 2.8523,
"step": 123500
},
{
"epoch": 2.94,
"learning_rate": 2.347608675063927e-05,
"loss": 2.8325,
"step": 124000
},
{
"epoch": 2.95,
"learning_rate": 2.3412949458597724e-05,
"loss": 2.8512,
"step": 124500
},
{
"epoch": 2.96,
"learning_rate": 2.3349812166556175e-05,
"loss": 2.852,
"step": 125000
},
{
"epoch": 2.97,
"learning_rate": 2.328667487451463e-05,
"loss": 2.8773,
"step": 125500
},
{
"epoch": 2.98,
"learning_rate": 2.322353758247309e-05,
"loss": 2.8292,
"step": 126000
},
{
"epoch": 3.0,
"learning_rate": 2.3160400290431544e-05,
"loss": 2.871,
"step": 126500
},
{
"epoch": 3.01,
"learning_rate": 2.309726299839e-05,
"loss": 2.7825,
"step": 127000
},
{
"epoch": 3.02,
"learning_rate": 2.3034125706348454e-05,
"loss": 2.7206,
"step": 127500
},
{
"epoch": 3.03,
"learning_rate": 2.2970988414306913e-05,
"loss": 2.7494,
"step": 128000
},
{
"epoch": 3.04,
"learning_rate": 2.2907851122265368e-05,
"loss": 2.7312,
"step": 128500
},
{
"epoch": 3.05,
"learning_rate": 2.2844713830223823e-05,
"loss": 2.7421,
"step": 129000
},
{
"epoch": 3.07,
"learning_rate": 2.2781576538182278e-05,
"loss": 2.7408,
"step": 129500
},
{
"epoch": 3.08,
"learning_rate": 2.2718439246140737e-05,
"loss": 2.7545,
"step": 130000
},
{
"epoch": 3.08,
"eval_loss": 3.13046932220459,
"eval_runtime": 113.5707,
"eval_samples_per_second": 165.289,
"eval_steps_per_second": 20.666,
"step": 130000
},
{
"epoch": 3.09,
"learning_rate": 2.265530195409919e-05,
"loss": 2.7526,
"step": 130500
},
{
"epoch": 3.1,
"learning_rate": 2.2592164662057647e-05,
"loss": 2.7588,
"step": 131000
},
{
"epoch": 3.11,
"learning_rate": 2.2529027370016102e-05,
"loss": 2.7342,
"step": 131500
},
{
"epoch": 3.13,
"learning_rate": 2.246589007797456e-05,
"loss": 2.7385,
"step": 132000
},
{
"epoch": 3.14,
"learning_rate": 2.2402752785933015e-05,
"loss": 2.7368,
"step": 132500
},
{
"epoch": 3.15,
"learning_rate": 2.2339615493891467e-05,
"loss": 2.7504,
"step": 133000
},
{
"epoch": 3.16,
"learning_rate": 2.2276478201849922e-05,
"loss": 2.7547,
"step": 133500
},
{
"epoch": 3.17,
"learning_rate": 2.2213340909808377e-05,
"loss": 2.7647,
"step": 134000
},
{
"epoch": 3.18,
"learning_rate": 2.2150203617766836e-05,
"loss": 2.7666,
"step": 134500
},
{
"epoch": 3.2,
"learning_rate": 2.208706632572529e-05,
"loss": 2.7559,
"step": 135000
},
{
"epoch": 3.21,
"learning_rate": 2.2023929033683746e-05,
"loss": 2.7673,
"step": 135500
},
{
"epoch": 3.22,
"learning_rate": 2.19607917416422e-05,
"loss": 2.76,
"step": 136000
},
{
"epoch": 3.23,
"learning_rate": 2.189765444960066e-05,
"loss": 2.7574,
"step": 136500
},
{
"epoch": 3.24,
"learning_rate": 2.1834517157559115e-05,
"loss": 2.7698,
"step": 137000
},
{
"epoch": 3.26,
"learning_rate": 2.177137986551757e-05,
"loss": 2.7619,
"step": 137500
},
{
"epoch": 3.27,
"learning_rate": 2.1708242573476025e-05,
"loss": 2.7511,
"step": 138000
},
{
"epoch": 3.28,
"learning_rate": 2.1645105281434484e-05,
"loss": 2.7578,
"step": 138500
},
{
"epoch": 3.29,
"learning_rate": 2.158196798939294e-05,
"loss": 2.7699,
"step": 139000
},
{
"epoch": 3.3,
"learning_rate": 2.1518830697351394e-05,
"loss": 2.7586,
"step": 139500
},
{
"epoch": 3.31,
"learning_rate": 2.145569340530985e-05,
"loss": 2.761,
"step": 140000
},
{
"epoch": 3.31,
"eval_loss": 3.1274259090423584,
"eval_runtime": 113.556,
"eval_samples_per_second": 165.31,
"eval_steps_per_second": 20.668,
"step": 140000
},
{
"epoch": 3.33,
"learning_rate": 2.1392556113268307e-05,
"loss": 2.66,
"step": 140500
},
{
"epoch": 3.34,
"learning_rate": 2.1329418821226756e-05,
"loss": 2.6439,
"step": 141000
},
{
"epoch": 3.35,
"learning_rate": 2.1266281529185214e-05,
"loss": 2.6605,
"step": 141500
},
{
"epoch": 3.36,
"learning_rate": 2.120314423714367e-05,
"loss": 2.6519,
"step": 142000
},
{
"epoch": 3.37,
"learning_rate": 2.1140006945102124e-05,
"loss": 2.6745,
"step": 142500
},
{
"epoch": 3.39,
"learning_rate": 2.107686965306058e-05,
"loss": 2.6932,
"step": 143000
},
{
"epoch": 3.4,
"learning_rate": 2.1013732361019038e-05,
"loss": 2.6881,
"step": 143500
},
{
"epoch": 3.41,
"learning_rate": 2.0950595068977493e-05,
"loss": 2.6835,
"step": 144000
},
{
"epoch": 3.42,
"learning_rate": 2.0887457776935948e-05,
"loss": 2.6964,
"step": 144500
},
{
"epoch": 3.43,
"learning_rate": 2.0824320484894403e-05,
"loss": 2.7124,
"step": 145000
},
{
"epoch": 3.44,
"learning_rate": 2.0761183192852862e-05,
"loss": 2.692,
"step": 145500
},
{
"epoch": 3.46,
"learning_rate": 2.0698045900811317e-05,
"loss": 2.7053,
"step": 146000
},
{
"epoch": 3.47,
"learning_rate": 2.0634908608769772e-05,
"loss": 2.6975,
"step": 146500
},
{
"epoch": 3.48,
"learning_rate": 2.0571771316728227e-05,
"loss": 2.7071,
"step": 147000
},
{
"epoch": 3.49,
"learning_rate": 2.0508634024686686e-05,
"loss": 2.7068,
"step": 147500
},
{
"epoch": 3.5,
"learning_rate": 2.044549673264514e-05,
"loss": 2.6956,
"step": 148000
},
{
"epoch": 3.52,
"learning_rate": 2.0382359440603596e-05,
"loss": 2.6934,
"step": 148500
},
{
"epoch": 3.53,
"learning_rate": 2.0319222148562048e-05,
"loss": 2.6956,
"step": 149000
},
{
"epoch": 3.54,
"learning_rate": 2.0256084856520503e-05,
"loss": 2.7062,
"step": 149500
},
{
"epoch": 3.55,
"learning_rate": 2.019294756447896e-05,
"loss": 2.7073,
"step": 150000
},
{
"epoch": 3.55,
"eval_loss": 3.1325318813323975,
"eval_runtime": 112.8184,
"eval_samples_per_second": 166.391,
"eval_steps_per_second": 20.803,
"step": 150000
},
{
"epoch": 3.56,
"learning_rate": 2.0129810272437416e-05,
"loss": 2.7105,
"step": 150500
},
{
"epoch": 3.58,
"learning_rate": 2.006667298039587e-05,
"loss": 2.7315,
"step": 151000
},
{
"epoch": 3.59,
"learning_rate": 2.0003535688354326e-05,
"loss": 2.7288,
"step": 151500
},
{
"epoch": 3.6,
"learning_rate": 1.9940398396312785e-05,
"loss": 2.7153,
"step": 152000
},
{
"epoch": 3.61,
"learning_rate": 1.987726110427124e-05,
"loss": 2.727,
"step": 152500
},
{
"epoch": 3.62,
"learning_rate": 1.9814123812229695e-05,
"loss": 2.7083,
"step": 153000
},
{
"epoch": 3.63,
"learning_rate": 1.975098652018815e-05,
"loss": 2.6938,
"step": 153500
},
{
"epoch": 3.65,
"learning_rate": 1.968784922814661e-05,
"loss": 2.7121,
"step": 154000
},
{
"epoch": 3.66,
"learning_rate": 1.9624711936105064e-05,
"loss": 2.7315,
"step": 154500
},
{
"epoch": 3.67,
"learning_rate": 1.9561574644063516e-05,
"loss": 2.7117,
"step": 155000
},
{
"epoch": 3.68,
"learning_rate": 1.9498437352021974e-05,
"loss": 2.7038,
"step": 155500
},
{
"epoch": 3.69,
"learning_rate": 1.943530005998043e-05,
"loss": 2.6951,
"step": 156000
},
{
"epoch": 3.71,
"learning_rate": 1.9372162767938884e-05,
"loss": 2.7369,
"step": 156500
},
{
"epoch": 3.72,
"learning_rate": 1.930902547589734e-05,
"loss": 2.7149,
"step": 157000
},
{
"epoch": 3.73,
"learning_rate": 1.9245888183855798e-05,
"loss": 2.7213,
"step": 157500
},
{
"epoch": 3.74,
"learning_rate": 1.9182750891814253e-05,
"loss": 2.7177,
"step": 158000
},
{
"epoch": 3.75,
"learning_rate": 1.9119613599772708e-05,
"loss": 2.7446,
"step": 158500
},
{
"epoch": 3.76,
"learning_rate": 1.9056476307731163e-05,
"loss": 2.7098,
"step": 159000
},
{
"epoch": 3.78,
"learning_rate": 1.899333901568962e-05,
"loss": 2.7229,
"step": 159500
},
{
"epoch": 3.79,
"learning_rate": 1.8930201723648073e-05,
"loss": 2.707,
"step": 160000
},
{
"epoch": 3.79,
"eval_loss": 3.127014398574829,
"eval_runtime": 112.7034,
"eval_samples_per_second": 166.561,
"eval_steps_per_second": 20.825,
"step": 160000
},
{
"epoch": 3.8,
"learning_rate": 1.886706443160653e-05,
"loss": 2.7213,
"step": 160500
},
{
"epoch": 3.81,
"learning_rate": 1.8803927139564987e-05,
"loss": 2.7193,
"step": 161000
},
{
"epoch": 3.82,
"learning_rate": 1.8740789847523442e-05,
"loss": 2.7288,
"step": 161500
},
{
"epoch": 3.84,
"learning_rate": 1.8677652555481897e-05,
"loss": 2.7379,
"step": 162000
},
{
"epoch": 3.85,
"learning_rate": 1.8614515263440352e-05,
"loss": 2.7309,
"step": 162500
},
{
"epoch": 3.86,
"learning_rate": 1.8551377971398807e-05,
"loss": 2.7283,
"step": 163000
},
{
"epoch": 3.87,
"learning_rate": 1.8488240679357263e-05,
"loss": 2.7326,
"step": 163500
},
{
"epoch": 3.88,
"learning_rate": 1.8425103387315718e-05,
"loss": 2.7326,
"step": 164000
},
{
"epoch": 3.89,
"learning_rate": 1.8361966095274176e-05,
"loss": 2.7295,
"step": 164500
},
{
"epoch": 3.91,
"learning_rate": 1.829882880323263e-05,
"loss": 2.7498,
"step": 165000
},
{
"epoch": 3.92,
"learning_rate": 1.8235691511191086e-05,
"loss": 2.7174,
"step": 165500
},
{
"epoch": 3.93,
"learning_rate": 1.817255421914954e-05,
"loss": 2.7268,
"step": 166000
},
{
"epoch": 3.94,
"learning_rate": 1.8109416927108e-05,
"loss": 2.7283,
"step": 166500
},
{
"epoch": 3.95,
"learning_rate": 1.804627963506645e-05,
"loss": 2.7312,
"step": 167000
},
{
"epoch": 3.97,
"learning_rate": 1.798314234302491e-05,
"loss": 2.7393,
"step": 167500
},
{
"epoch": 3.98,
"learning_rate": 1.7920005050983365e-05,
"loss": 2.7335,
"step": 168000
},
{
"epoch": 3.99,
"learning_rate": 1.785686775894182e-05,
"loss": 2.7394,
"step": 168500
},
{
"epoch": 4.0,
"learning_rate": 1.7793730466900276e-05,
"loss": 2.7243,
"step": 169000
},
{
"epoch": 4.01,
"learning_rate": 1.7730593174858734e-05,
"loss": 2.6166,
"step": 169500
},
{
"epoch": 4.03,
"learning_rate": 1.766745588281719e-05,
"loss": 2.6252,
"step": 170000
},
{
"epoch": 4.03,
"eval_loss": 3.1331186294555664,
"eval_runtime": 112.7793,
"eval_samples_per_second": 166.449,
"eval_steps_per_second": 20.811,
"step": 170000
},
{
"epoch": 4.04,
"learning_rate": 1.760431859077564e-05,
"loss": 2.6119,
"step": 170500
},
{
"epoch": 4.05,
"learning_rate": 1.75411812987341e-05,
"loss": 2.6106,
"step": 171000
},
{
"epoch": 4.06,
"learning_rate": 1.7478044006692554e-05,
"loss": 2.6353,
"step": 171500
},
{
"epoch": 4.07,
"learning_rate": 1.741490671465101e-05,
"loss": 2.6192,
"step": 172000
},
{
"epoch": 4.08,
"learning_rate": 1.7351769422609465e-05,
"loss": 2.6269,
"step": 172500
},
{
"epoch": 4.1,
"learning_rate": 1.7288632130567923e-05,
"loss": 2.6145,
"step": 173000
},
{
"epoch": 4.11,
"learning_rate": 1.7225494838526378e-05,
"loss": 2.6366,
"step": 173500
},
{
"epoch": 4.12,
"learning_rate": 1.7162357546484833e-05,
"loss": 2.6273,
"step": 174000
},
{
"epoch": 4.13,
"learning_rate": 1.709922025444329e-05,
"loss": 2.6381,
"step": 174500
},
{
"epoch": 4.14,
"learning_rate": 1.7036082962401744e-05,
"loss": 2.6218,
"step": 175000
},
{
"epoch": 4.16,
"learning_rate": 1.69729456703602e-05,
"loss": 2.6406,
"step": 175500
},
{
"epoch": 4.17,
"learning_rate": 1.6909808378318654e-05,
"loss": 2.6366,
"step": 176000
},
{
"epoch": 4.18,
"learning_rate": 1.6846671086277112e-05,
"loss": 2.6445,
"step": 176500
},
{
"epoch": 4.19,
"learning_rate": 1.6783533794235567e-05,
"loss": 2.6649,
"step": 177000
},
{
"epoch": 4.2,
"learning_rate": 1.6720396502194022e-05,
"loss": 2.6351,
"step": 177500
},
{
"epoch": 4.21,
"learning_rate": 1.6657259210152478e-05,
"loss": 2.6261,
"step": 178000
},
{
"epoch": 4.23,
"learning_rate": 1.6594121918110933e-05,
"loss": 2.6413,
"step": 178500
},
{
"epoch": 4.24,
"learning_rate": 1.6530984626069388e-05,
"loss": 2.6418,
"step": 179000
},
{
"epoch": 4.25,
"learning_rate": 1.6467847334027843e-05,
"loss": 2.6263,
"step": 179500
},
{
"epoch": 4.26,
"learning_rate": 1.64047100419863e-05,
"loss": 2.6519,
"step": 180000
},
{
"epoch": 4.26,
"eval_loss": 3.13765549659729,
"eval_runtime": 112.7621,
"eval_samples_per_second": 166.474,
"eval_steps_per_second": 20.814,
"step": 180000
},
{
"epoch": 4.27,
"learning_rate": 1.6341572749944757e-05,
"loss": 2.6478,
"step": 180500
},
{
"epoch": 4.29,
"learning_rate": 1.627843545790321e-05,
"loss": 2.641,
"step": 181000
},
{
"epoch": 4.3,
"learning_rate": 1.6215298165861667e-05,
"loss": 2.649,
"step": 181500
},
{
"epoch": 4.31,
"learning_rate": 1.6152160873820125e-05,
"loss": 2.6318,
"step": 182000
},
{
"epoch": 4.32,
"learning_rate": 1.6089023581778577e-05,
"loss": 2.6499,
"step": 182500
},
{
"epoch": 4.33,
"learning_rate": 1.6025886289737035e-05,
"loss": 2.6527,
"step": 183000
},
{
"epoch": 4.34,
"learning_rate": 1.596274899769549e-05,
"loss": 2.6351,
"step": 183500
},
{
"epoch": 4.36,
"learning_rate": 1.5899611705653946e-05,
"loss": 2.6559,
"step": 184000
},
{
"epoch": 4.37,
"learning_rate": 1.58364744136124e-05,
"loss": 2.6485,
"step": 184500
},
{
"epoch": 4.38,
"learning_rate": 1.5773337121570856e-05,
"loss": 2.6551,
"step": 185000
},
{
"epoch": 4.39,
"learning_rate": 1.5710199829529314e-05,
"loss": 2.6637,
"step": 185500
},
{
"epoch": 4.4,
"learning_rate": 1.564706253748777e-05,
"loss": 2.6371,
"step": 186000
},
{
"epoch": 4.42,
"learning_rate": 1.5583925245446225e-05,
"loss": 2.6435,
"step": 186500
},
{
"epoch": 4.43,
"learning_rate": 1.552078795340468e-05,
"loss": 2.6611,
"step": 187000
},
{
"epoch": 4.44,
"learning_rate": 1.5457650661363135e-05,
"loss": 2.6419,
"step": 187500
},
{
"epoch": 4.45,
"learning_rate": 1.539451336932159e-05,
"loss": 2.6687,
"step": 188000
},
{
"epoch": 4.46,
"learning_rate": 1.533137607728005e-05,
"loss": 2.6461,
"step": 188500
},
{
"epoch": 4.47,
"learning_rate": 1.5268238785238503e-05,
"loss": 2.6568,
"step": 189000
},
{
"epoch": 4.49,
"learning_rate": 1.5205101493196959e-05,
"loss": 2.6263,
"step": 189500
},
{
"epoch": 4.5,
"learning_rate": 1.5141964201155415e-05,
"loss": 2.6687,
"step": 190000
},
{
"epoch": 4.5,
"eval_loss": 3.1315951347351074,
"eval_runtime": 112.9501,
"eval_samples_per_second": 166.197,
"eval_steps_per_second": 20.779,
"step": 190000
},
{
"epoch": 4.51,
"learning_rate": 1.5078826909113869e-05,
"loss": 2.649,
"step": 190500
},
{
"epoch": 4.52,
"learning_rate": 1.5015689617072324e-05,
"loss": 2.6748,
"step": 191000
},
{
"epoch": 4.53,
"learning_rate": 1.495255232503078e-05,
"loss": 2.66,
"step": 191500
},
{
"epoch": 4.55,
"learning_rate": 1.4889415032989236e-05,
"loss": 2.6656,
"step": 192000
},
{
"epoch": 4.56,
"learning_rate": 1.4826277740947693e-05,
"loss": 2.6665,
"step": 192500
},
{
"epoch": 4.57,
"learning_rate": 1.4763140448906148e-05,
"loss": 2.6698,
"step": 193000
},
{
"epoch": 4.58,
"learning_rate": 1.4700003156864605e-05,
"loss": 2.6561,
"step": 193500
},
{
"epoch": 4.59,
"learning_rate": 1.463686586482306e-05,
"loss": 2.671,
"step": 194000
},
{
"epoch": 4.61,
"learning_rate": 1.4573728572781513e-05,
"loss": 2.6795,
"step": 194500
},
{
"epoch": 4.62,
"learning_rate": 1.451059128073997e-05,
"loss": 2.6709,
"step": 195000
},
{
"epoch": 4.63,
"learning_rate": 1.4447453988698425e-05,
"loss": 2.6818,
"step": 195500
},
{
"epoch": 4.64,
"learning_rate": 1.4384316696656882e-05,
"loss": 2.6808,
"step": 196000
},
{
"epoch": 4.65,
"learning_rate": 1.4321179404615337e-05,
"loss": 2.6767,
"step": 196500
},
{
"epoch": 4.66,
"learning_rate": 1.4258042112573794e-05,
"loss": 2.6861,
"step": 197000
},
{
"epoch": 4.68,
"learning_rate": 1.4194904820532249e-05,
"loss": 2.6694,
"step": 197500
},
{
"epoch": 4.69,
"learning_rate": 1.4131767528490706e-05,
"loss": 2.6766,
"step": 198000
},
{
"epoch": 4.7,
"learning_rate": 1.4068630236449159e-05,
"loss": 2.6597,
"step": 198500
},
{
"epoch": 4.71,
"learning_rate": 1.4005492944407614e-05,
"loss": 2.6551,
"step": 199000
},
{
"epoch": 4.72,
"learning_rate": 1.3942355652366071e-05,
"loss": 2.6514,
"step": 199500
},
{
"epoch": 4.74,
"learning_rate": 1.3879218360324526e-05,
"loss": 2.6788,
"step": 200000
},
{
"epoch": 4.74,
"eval_loss": 3.1263821125030518,
"eval_runtime": 112.9792,
"eval_samples_per_second": 166.155,
"eval_steps_per_second": 20.774,
"step": 200000
},
{
"epoch": 4.75,
"learning_rate": 1.3816081068282983e-05,
"loss": 2.6777,
"step": 200500
},
{
"epoch": 4.76,
"learning_rate": 1.3752943776241438e-05,
"loss": 2.6712,
"step": 201000
},
{
"epoch": 4.77,
"learning_rate": 1.3689806484199895e-05,
"loss": 2.6751,
"step": 201500
},
{
"epoch": 4.78,
"learning_rate": 1.362666919215835e-05,
"loss": 2.677,
"step": 202000
},
{
"epoch": 4.79,
"learning_rate": 1.3563531900116805e-05,
"loss": 2.6732,
"step": 202500
},
{
"epoch": 4.81,
"learning_rate": 1.350039460807526e-05,
"loss": 2.6634,
"step": 203000
},
{
"epoch": 4.82,
"learning_rate": 1.3437257316033717e-05,
"loss": 2.6684,
"step": 203500
},
{
"epoch": 4.83,
"learning_rate": 1.3374120023992172e-05,
"loss": 2.6892,
"step": 204000
},
{
"epoch": 4.84,
"learning_rate": 1.3310982731950629e-05,
"loss": 2.676,
"step": 204500
},
{
"epoch": 4.85,
"learning_rate": 1.3247845439909084e-05,
"loss": 2.6605,
"step": 205000
},
{
"epoch": 4.87,
"learning_rate": 1.318470814786754e-05,
"loss": 2.6773,
"step": 205500
},
{
"epoch": 4.88,
"learning_rate": 1.3121570855825996e-05,
"loss": 2.6702,
"step": 206000
},
{
"epoch": 4.89,
"learning_rate": 1.305843356378445e-05,
"loss": 2.6662,
"step": 206500
},
{
"epoch": 4.9,
"learning_rate": 1.2995296271742906e-05,
"loss": 2.6775,
"step": 207000
},
{
"epoch": 4.91,
"learning_rate": 1.2932158979701361e-05,
"loss": 2.6829,
"step": 207500
},
{
"epoch": 4.92,
"learning_rate": 1.2869021687659818e-05,
"loss": 2.6679,
"step": 208000
},
{
"epoch": 4.94,
"learning_rate": 1.2805884395618273e-05,
"loss": 2.6671,
"step": 208500
},
{
"epoch": 4.95,
"learning_rate": 1.274274710357673e-05,
"loss": 2.6746,
"step": 209000
},
{
"epoch": 4.96,
"learning_rate": 1.2679609811535185e-05,
"loss": 2.6955,
"step": 209500
},
{
"epoch": 4.97,
"learning_rate": 1.2616472519493642e-05,
"loss": 2.6812,
"step": 210000
},
{
"epoch": 4.97,
"eval_loss": 3.1202192306518555,
"eval_runtime": 112.9566,
"eval_samples_per_second": 166.188,
"eval_steps_per_second": 20.778,
"step": 210000
},
{
"epoch": 4.98,
"learning_rate": 1.2553335227452095e-05,
"loss": 2.6648,
"step": 210500
},
{
"epoch": 5.0,
"learning_rate": 1.249019793541055e-05,
"loss": 2.6742,
"step": 211000
},
{
"epoch": 5.01,
"learning_rate": 1.2427060643369007e-05,
"loss": 2.594,
"step": 211500
},
{
"epoch": 5.02,
"learning_rate": 1.2363923351327462e-05,
"loss": 2.5158,
"step": 212000
},
{
"epoch": 5.03,
"learning_rate": 1.2300786059285919e-05,
"loss": 2.5283,
"step": 212500
},
{
"epoch": 5.04,
"learning_rate": 1.2237648767244374e-05,
"loss": 2.5491,
"step": 213000
},
{
"epoch": 5.05,
"learning_rate": 1.217451147520283e-05,
"loss": 2.5441,
"step": 213500
},
{
"epoch": 5.07,
"learning_rate": 1.2111374183161284e-05,
"loss": 2.5604,
"step": 214000
},
{
"epoch": 5.08,
"learning_rate": 1.204823689111974e-05,
"loss": 2.513,
"step": 214500
},
{
"epoch": 5.09,
"learning_rate": 1.1985099599078196e-05,
"loss": 2.5637,
"step": 215000
},
{
"epoch": 5.1,
"learning_rate": 1.1921962307036651e-05,
"loss": 2.5589,
"step": 215500
},
{
"epoch": 5.11,
"learning_rate": 1.1858825014995108e-05,
"loss": 2.5188,
"step": 216000
},
{
"epoch": 5.13,
"learning_rate": 1.1795687722953563e-05,
"loss": 2.5495,
"step": 216500
},
{
"epoch": 5.14,
"learning_rate": 1.173255043091202e-05,
"loss": 2.5539,
"step": 217000
},
{
"epoch": 5.15,
"learning_rate": 1.1669413138870475e-05,
"loss": 2.5574,
"step": 217500
},
{
"epoch": 5.16,
"learning_rate": 1.160627584682893e-05,
"loss": 2.5429,
"step": 218000
},
{
"epoch": 5.17,
"learning_rate": 1.1543138554787385e-05,
"loss": 2.5372,
"step": 218500
},
{
"epoch": 5.19,
"learning_rate": 1.1480001262745842e-05,
"loss": 2.5383,
"step": 219000
},
{
"epoch": 5.2,
"learning_rate": 1.1416863970704297e-05,
"loss": 2.5559,
"step": 219500
},
{
"epoch": 5.21,
"learning_rate": 1.1353726678662754e-05,
"loss": 2.545,
"step": 220000
},
{
"epoch": 5.21,
"eval_loss": 3.1433441638946533,
"eval_runtime": 112.9981,
"eval_samples_per_second": 166.127,
"eval_steps_per_second": 20.77,
"step": 220000
},
{
"epoch": 5.22,
"learning_rate": 1.1290589386621209e-05,
"loss": 2.5437,
"step": 220500
},
{
"epoch": 5.23,
"learning_rate": 1.1227452094579664e-05,
"loss": 2.5765,
"step": 221000
},
{
"epoch": 5.24,
"learning_rate": 1.1164314802538121e-05,
"loss": 2.5522,
"step": 221500
},
{
"epoch": 5.26,
"learning_rate": 1.1101177510496574e-05,
"loss": 2.5466,
"step": 222000
},
{
"epoch": 5.27,
"learning_rate": 1.1038040218455031e-05,
"loss": 2.5625,
"step": 222500
},
{
"epoch": 5.28,
"learning_rate": 1.0974902926413486e-05,
"loss": 2.5546,
"step": 223000
},
{
"epoch": 5.29,
"learning_rate": 1.0911765634371943e-05,
"loss": 2.5455,
"step": 223500
},
{
"epoch": 5.3,
"learning_rate": 1.0848628342330398e-05,
"loss": 2.5645,
"step": 224000
},
{
"epoch": 5.32,
"learning_rate": 1.0785491050288855e-05,
"loss": 2.5662,
"step": 224500
},
{
"epoch": 5.33,
"learning_rate": 1.072235375824731e-05,
"loss": 2.5446,
"step": 225000
},
{
"epoch": 5.34,
"learning_rate": 1.0659216466205767e-05,
"loss": 2.5654,
"step": 225500
},
{
"epoch": 5.35,
"learning_rate": 1.059607917416422e-05,
"loss": 2.5521,
"step": 226000
},
{
"epoch": 5.36,
"learning_rate": 1.0532941882122675e-05,
"loss": 2.5779,
"step": 226500
},
{
"epoch": 5.37,
"learning_rate": 1.0469804590081132e-05,
"loss": 2.5456,
"step": 227000
},
{
"epoch": 5.39,
"learning_rate": 1.0406667298039587e-05,
"loss": 2.5721,
"step": 227500
},
{
"epoch": 5.4,
"learning_rate": 1.0343530005998044e-05,
"loss": 2.5497,
"step": 228000
},
{
"epoch": 5.41,
"learning_rate": 1.02803927139565e-05,
"loss": 2.5528,
"step": 228500
},
{
"epoch": 5.42,
"learning_rate": 1.0217255421914956e-05,
"loss": 2.5854,
"step": 229000
},
{
"epoch": 5.43,
"learning_rate": 1.0154118129873411e-05,
"loss": 2.5731,
"step": 229500
},
{
"epoch": 5.45,
"learning_rate": 1.0090980837831865e-05,
"loss": 2.5575,
"step": 230000
},
{
"epoch": 5.45,
"eval_loss": 3.1408019065856934,
"eval_runtime": 113.0201,
"eval_samples_per_second": 166.094,
"eval_steps_per_second": 20.766,
"step": 230000
},
{
"epoch": 5.46,
"learning_rate": 1.0027843545790321e-05,
"loss": 2.56,
"step": 230500
},
{
"epoch": 5.47,
"learning_rate": 9.964706253748776e-06,
"loss": 2.5605,
"step": 231000
},
{
"epoch": 5.48,
"learning_rate": 9.901568961707233e-06,
"loss": 2.5527,
"step": 231500
},
{
"epoch": 5.49,
"learning_rate": 9.838431669665688e-06,
"loss": 2.5613,
"step": 232000
},
{
"epoch": 5.5,
"learning_rate": 9.775294377624145e-06,
"loss": 2.5698,
"step": 232500
},
{
"epoch": 5.52,
"learning_rate": 9.7121570855826e-06,
"loss": 2.5681,
"step": 233000
},
{
"epoch": 5.53,
"learning_rate": 9.649019793541055e-06,
"loss": 2.5763,
"step": 233500
},
{
"epoch": 5.54,
"learning_rate": 9.585882501499512e-06,
"loss": 2.5602,
"step": 234000
},
{
"epoch": 5.55,
"learning_rate": 9.522745209457967e-06,
"loss": 2.5559,
"step": 234500
},
{
"epoch": 5.56,
"learning_rate": 9.459607917416422e-06,
"loss": 2.5877,
"step": 235000
},
{
"epoch": 5.58,
"learning_rate": 9.396470625374878e-06,
"loss": 2.5779,
"step": 235500
},
{
"epoch": 5.59,
"learning_rate": 9.333333333333334e-06,
"loss": 2.5723,
"step": 236000
},
{
"epoch": 5.6,
"learning_rate": 9.27019604129179e-06,
"loss": 2.5695,
"step": 236500
},
{
"epoch": 5.61,
"learning_rate": 9.207058749250245e-06,
"loss": 2.576,
"step": 237000
},
{
"epoch": 5.62,
"learning_rate": 9.143921457208701e-06,
"loss": 2.5758,
"step": 237500
},
{
"epoch": 5.64,
"learning_rate": 9.080784165167156e-06,
"loss": 2.5674,
"step": 238000
},
{
"epoch": 5.65,
"learning_rate": 9.017646873125613e-06,
"loss": 2.5822,
"step": 238500
},
{
"epoch": 5.66,
"learning_rate": 8.954509581084068e-06,
"loss": 2.5668,
"step": 239000
},
{
"epoch": 5.67,
"learning_rate": 8.891372289042523e-06,
"loss": 2.5873,
"step": 239500
},
{
"epoch": 5.68,
"learning_rate": 8.82823499700098e-06,
"loss": 2.5795,
"step": 240000
},
{
"epoch": 5.68,
"eval_loss": 3.1380364894866943,
"eval_runtime": 112.9332,
"eval_samples_per_second": 166.222,
"eval_steps_per_second": 20.782,
"step": 240000
},
{
"epoch": 5.69,
"learning_rate": 8.765097704959435e-06,
"loss": 2.5608,
"step": 240500
},
{
"epoch": 5.71,
"learning_rate": 8.70196041291789e-06,
"loss": 2.5768,
"step": 241000
},
{
"epoch": 5.72,
"learning_rate": 8.638823120876346e-06,
"loss": 2.5887,
"step": 241500
},
{
"epoch": 5.73,
"learning_rate": 8.575685828834802e-06,
"loss": 2.5603,
"step": 242000
},
{
"epoch": 5.74,
"learning_rate": 8.512548536793257e-06,
"loss": 2.5866,
"step": 242500
},
{
"epoch": 5.75,
"learning_rate": 8.449411244751713e-06,
"loss": 2.5748,
"step": 243000
},
{
"epoch": 5.77,
"learning_rate": 8.38627395271017e-06,
"loss": 2.5759,
"step": 243500
},
{
"epoch": 5.78,
"learning_rate": 8.323136660668624e-06,
"loss": 2.5631,
"step": 244000
},
{
"epoch": 5.79,
"learning_rate": 8.259999368627081e-06,
"loss": 2.5805,
"step": 244500
},
{
"epoch": 5.8,
"learning_rate": 8.196862076585536e-06,
"loss": 2.5741,
"step": 245000
},
{
"epoch": 5.81,
"learning_rate": 8.133724784543992e-06,
"loss": 2.5731,
"step": 245500
},
{
"epoch": 5.82,
"learning_rate": 8.070587492502447e-06,
"loss": 2.5883,
"step": 246000
},
{
"epoch": 5.84,
"learning_rate": 8.007450200460903e-06,
"loss": 2.5855,
"step": 246500
},
{
"epoch": 5.85,
"learning_rate": 7.944312908419359e-06,
"loss": 2.593,
"step": 247000
},
{
"epoch": 5.86,
"learning_rate": 7.881175616377814e-06,
"loss": 2.5795,
"step": 247500
},
{
"epoch": 5.87,
"learning_rate": 7.81803832433627e-06,
"loss": 2.5793,
"step": 248000
},
{
"epoch": 5.88,
"learning_rate": 7.754901032294726e-06,
"loss": 2.5808,
"step": 248500
},
{
"epoch": 5.9,
"learning_rate": 7.69176374025318e-06,
"loss": 2.5725,
"step": 249000
},
{
"epoch": 5.91,
"learning_rate": 7.628626448211637e-06,
"loss": 2.5766,
"step": 249500
},
{
"epoch": 5.92,
"learning_rate": 7.5654891561700926e-06,
"loss": 2.5882,
"step": 250000
},
{
"epoch": 5.92,
"eval_loss": 3.132246732711792,
"eval_runtime": 112.9084,
"eval_samples_per_second": 166.259,
"eval_steps_per_second": 20.787,
"step": 250000
},
{
"epoch": 5.93,
"learning_rate": 7.5023518641285485e-06,
"loss": 2.5599,
"step": 250500
},
{
"epoch": 5.94,
"learning_rate": 7.439214572087004e-06,
"loss": 2.563,
"step": 251000
},
{
"epoch": 5.95,
"learning_rate": 7.3760772800454596e-06,
"loss": 2.5871,
"step": 251500
},
{
"epoch": 5.97,
"learning_rate": 7.3129399880039155e-06,
"loss": 2.5899,
"step": 252000
},
{
"epoch": 5.98,
"learning_rate": 7.2498026959623715e-06,
"loss": 2.5656,
"step": 252500
},
{
"epoch": 5.99,
"learning_rate": 7.186665403920826e-06,
"loss": 2.5768,
"step": 253000
},
{
"epoch": 6.0,
"learning_rate": 7.123528111879282e-06,
"loss": 2.5688,
"step": 253500
},
{
"epoch": 6.01,
"learning_rate": 7.060390819837738e-06,
"loss": 2.4722,
"step": 254000
},
{
"epoch": 6.03,
"learning_rate": 6.997253527796194e-06,
"loss": 2.4748,
"step": 254500
},
{
"epoch": 6.04,
"learning_rate": 6.934116235754649e-06,
"loss": 2.4598,
"step": 255000
},
{
"epoch": 6.05,
"learning_rate": 6.870978943713105e-06,
"loss": 2.4573,
"step": 255500
},
{
"epoch": 6.06,
"learning_rate": 6.807841651671561e-06,
"loss": 2.485,
"step": 256000
},
{
"epoch": 6.07,
"learning_rate": 6.7447043596300166e-06,
"loss": 2.4624,
"step": 256500
},
{
"epoch": 6.08,
"learning_rate": 6.681567067588472e-06,
"loss": 2.4746,
"step": 257000
},
{
"epoch": 6.1,
"learning_rate": 6.618429775546928e-06,
"loss": 2.4594,
"step": 257500
},
{
"epoch": 6.11,
"learning_rate": 6.5552924835053836e-06,
"loss": 2.4745,
"step": 258000
},
{
"epoch": 6.12,
"learning_rate": 6.492155191463838e-06,
"loss": 2.4746,
"step": 258500
},
{
"epoch": 6.13,
"learning_rate": 6.429017899422294e-06,
"loss": 2.484,
"step": 259000
},
{
"epoch": 6.14,
"learning_rate": 6.36588060738075e-06,
"loss": 2.4965,
"step": 259500
},
{
"epoch": 6.16,
"learning_rate": 6.302743315339206e-06,
"loss": 2.48,
"step": 260000
},
{
"epoch": 6.16,
"eval_loss": 3.149815797805786,
"eval_runtime": 112.7275,
"eval_samples_per_second": 166.525,
"eval_steps_per_second": 20.82,
"step": 260000
},
{
"epoch": 6.17,
"learning_rate": 6.239606023297661e-06,
"loss": 2.4824,
"step": 260500
},
{
"epoch": 6.18,
"learning_rate": 6.176468731256117e-06,
"loss": 2.4763,
"step": 261000
},
{
"epoch": 6.19,
"learning_rate": 6.113331439214573e-06,
"loss": 2.4669,
"step": 261500
},
{
"epoch": 6.2,
"learning_rate": 6.050194147173029e-06,
"loss": 2.4716,
"step": 262000
},
{
"epoch": 6.22,
"learning_rate": 5.987056855131484e-06,
"loss": 2.486,
"step": 262500
},
{
"epoch": 6.23,
"learning_rate": 5.92391956308994e-06,
"loss": 2.4668,
"step": 263000
},
{
"epoch": 6.24,
"learning_rate": 5.860782271048396e-06,
"loss": 2.4778,
"step": 263500
},
{
"epoch": 6.25,
"learning_rate": 5.797644979006851e-06,
"loss": 2.4775,
"step": 264000
},
{
"epoch": 6.26,
"learning_rate": 5.734507686965306e-06,
"loss": 2.4832,
"step": 264500
},
{
"epoch": 6.27,
"learning_rate": 5.671370394923762e-06,
"loss": 2.5047,
"step": 265000
},
{
"epoch": 6.29,
"learning_rate": 5.608233102882218e-06,
"loss": 2.4541,
"step": 265500
},
{
"epoch": 6.3,
"learning_rate": 5.545095810840674e-06,
"loss": 2.4823,
"step": 266000
},
{
"epoch": 6.31,
"learning_rate": 5.481958518799129e-06,
"loss": 2.4952,
"step": 266500
},
{
"epoch": 6.32,
"learning_rate": 5.418821226757585e-06,
"loss": 2.4787,
"step": 267000
},
{
"epoch": 6.33,
"learning_rate": 5.355683934716041e-06,
"loss": 2.4751,
"step": 267500
},
{
"epoch": 6.35,
"learning_rate": 5.292546642674497e-06,
"loss": 2.4819,
"step": 268000
},
{
"epoch": 6.36,
"learning_rate": 5.229409350632951e-06,
"loss": 2.4931,
"step": 268500
},
{
"epoch": 6.37,
"learning_rate": 5.166272058591407e-06,
"loss": 2.4819,
"step": 269000
},
{
"epoch": 6.38,
"learning_rate": 5.103134766549863e-06,
"loss": 2.4842,
"step": 269500
},
{
"epoch": 6.39,
"learning_rate": 5.039997474508319e-06,
"loss": 2.4701,
"step": 270000
},
{
"epoch": 6.39,
"eval_loss": 3.150057792663574,
"eval_runtime": 112.8196,
"eval_samples_per_second": 166.39,
"eval_steps_per_second": 20.803,
"step": 270000
},
{
"epoch": 6.4,
"learning_rate": 4.976860182466775e-06,
"loss": 2.4924,
"step": 270500
},
{
"epoch": 6.42,
"learning_rate": 4.91372289042523e-06,
"loss": 2.484,
"step": 271000
},
{
"epoch": 6.43,
"learning_rate": 4.850585598383686e-06,
"loss": 2.5076,
"step": 271500
},
{
"epoch": 6.44,
"learning_rate": 4.787448306342141e-06,
"loss": 2.4958,
"step": 272000
},
{
"epoch": 6.45,
"learning_rate": 4.724311014300597e-06,
"loss": 2.4692,
"step": 272500
},
{
"epoch": 6.46,
"learning_rate": 4.661173722259053e-06,
"loss": 2.4638,
"step": 273000
},
{
"epoch": 6.48,
"learning_rate": 4.598036430217509e-06,
"loss": 2.4956,
"step": 273500
},
{
"epoch": 6.49,
"learning_rate": 4.534899138175964e-06,
"loss": 2.4985,
"step": 274000
},
{
"epoch": 6.5,
"learning_rate": 4.47176184613442e-06,
"loss": 2.5003,
"step": 274500
},
{
"epoch": 6.51,
"learning_rate": 4.408624554092875e-06,
"loss": 2.4914,
"step": 275000
},
{
"epoch": 6.52,
"learning_rate": 4.345487262051331e-06,
"loss": 2.4981,
"step": 275500
},
{
"epoch": 6.53,
"learning_rate": 4.282349970009787e-06,
"loss": 2.5008,
"step": 276000
},
{
"epoch": 6.55,
"learning_rate": 4.219212677968242e-06,
"loss": 2.5063,
"step": 276500
},
{
"epoch": 6.56,
"learning_rate": 4.156075385926698e-06,
"loss": 2.4841,
"step": 277000
},
{
"epoch": 6.57,
"learning_rate": 4.092938093885154e-06,
"loss": 2.4833,
"step": 277500
},
{
"epoch": 6.58,
"learning_rate": 4.029800801843609e-06,
"loss": 2.4839,
"step": 278000
},
{
"epoch": 6.59,
"learning_rate": 3.966663509802065e-06,
"loss": 2.489,
"step": 278500
},
{
"epoch": 6.61,
"learning_rate": 3.90352621776052e-06,
"loss": 2.4897,
"step": 279000
},
{
"epoch": 6.62,
"learning_rate": 3.840388925718976e-06,
"loss": 2.5142,
"step": 279500
},
{
"epoch": 6.63,
"learning_rate": 3.7772516336774316e-06,
"loss": 2.4862,
"step": 280000
},
{
"epoch": 6.63,
"eval_loss": 3.1480441093444824,
"eval_runtime": 112.7656,
"eval_samples_per_second": 166.469,
"eval_steps_per_second": 20.813,
"step": 280000
},
{
"epoch": 6.64,
"learning_rate": 3.7141143416358875e-06,
"loss": 2.4941,
"step": 280500
},
{
"epoch": 6.65,
"learning_rate": 3.650977049594343e-06,
"loss": 2.4823,
"step": 281000
},
{
"epoch": 6.66,
"learning_rate": 3.587839757552799e-06,
"loss": 2.4742,
"step": 281500
},
{
"epoch": 6.68,
"learning_rate": 3.5247024655112545e-06,
"loss": 2.4932,
"step": 282000
},
{
"epoch": 6.69,
"learning_rate": 3.4615651734697105e-06,
"loss": 2.4958,
"step": 282500
},
{
"epoch": 6.7,
"learning_rate": 3.3984278814281656e-06,
"loss": 2.4956,
"step": 283000
},
{
"epoch": 6.71,
"learning_rate": 3.3352905893866215e-06,
"loss": 2.4675,
"step": 283500
},
{
"epoch": 6.72,
"learning_rate": 3.272153297345077e-06,
"loss": 2.5031,
"step": 284000
},
{
"epoch": 6.74,
"learning_rate": 3.209016005303533e-06,
"loss": 2.4822,
"step": 284500
},
{
"epoch": 6.75,
"learning_rate": 3.1458787132619886e-06,
"loss": 2.4907,
"step": 285000
},
{
"epoch": 6.76,
"learning_rate": 3.082741421220444e-06,
"loss": 2.4978,
"step": 285500
},
{
"epoch": 6.77,
"learning_rate": 3.0196041291788996e-06,
"loss": 2.5003,
"step": 286000
},
{
"epoch": 6.78,
"learning_rate": 2.9564668371373556e-06,
"loss": 2.4952,
"step": 286500
},
{
"epoch": 6.8,
"learning_rate": 2.893329545095811e-06,
"loss": 2.4808,
"step": 287000
},
{
"epoch": 6.81,
"learning_rate": 2.830192253054267e-06,
"loss": 2.4982,
"step": 287500
},
{
"epoch": 6.82,
"learning_rate": 2.767054961012722e-06,
"loss": 2.4833,
"step": 288000
},
{
"epoch": 6.83,
"learning_rate": 2.703917668971178e-06,
"loss": 2.4821,
"step": 288500
},
{
"epoch": 6.84,
"learning_rate": 2.6407803769296336e-06,
"loss": 2.4752,
"step": 289000
},
{
"epoch": 6.85,
"learning_rate": 2.5776430848880896e-06,
"loss": 2.5009,
"step": 289500
},
{
"epoch": 6.87,
"learning_rate": 2.514505792846545e-06,
"loss": 2.4833,
"step": 290000
},
{
"epoch": 6.87,
"eval_loss": 3.1463212966918945,
"eval_runtime": 112.8484,
"eval_samples_per_second": 166.347,
"eval_steps_per_second": 20.798,
"step": 290000
},
{
"epoch": 6.88,
"learning_rate": 2.4513685008050007e-06,
"loss": 2.4999,
"step": 290500
},
{
"epoch": 6.89,
"learning_rate": 2.388231208763456e-06,
"loss": 2.5123,
"step": 291000
},
{
"epoch": 6.9,
"learning_rate": 2.3250939167219117e-06,
"loss": 2.5084,
"step": 291500
},
{
"epoch": 6.91,
"learning_rate": 2.2619566246803677e-06,
"loss": 2.4901,
"step": 292000
},
{
"epoch": 6.93,
"learning_rate": 2.198819332638823e-06,
"loss": 2.4825,
"step": 292500
},
{
"epoch": 6.94,
"learning_rate": 2.1356820405972787e-06,
"loss": 2.4869,
"step": 293000
},
{
"epoch": 6.95,
"learning_rate": 2.0725447485557347e-06,
"loss": 2.4868,
"step": 293500
},
{
"epoch": 6.96,
"learning_rate": 2.0094074565141902e-06,
"loss": 2.4949,
"step": 294000
},
{
"epoch": 6.97,
"learning_rate": 1.9462701644726457e-06,
"loss": 2.4966,
"step": 294500
},
{
"epoch": 6.98,
"learning_rate": 1.8831328724311015e-06,
"loss": 2.5215,
"step": 295000
},
{
"epoch": 7.0,
"learning_rate": 1.8199955803895572e-06,
"loss": 2.5083,
"step": 295500
},
{
"epoch": 7.01,
"learning_rate": 1.756858288348013e-06,
"loss": 2.4656,
"step": 296000
},
{
"epoch": 7.02,
"learning_rate": 1.6937209963064685e-06,
"loss": 2.4272,
"step": 296500
},
{
"epoch": 7.03,
"learning_rate": 1.6305837042649242e-06,
"loss": 2.4327,
"step": 297000
},
{
"epoch": 7.04,
"learning_rate": 1.5674464122233798e-06,
"loss": 2.431,
"step": 297500
},
{
"epoch": 7.06,
"learning_rate": 1.5043091201818355e-06,
"loss": 2.4326,
"step": 298000
},
{
"epoch": 7.07,
"learning_rate": 1.4411718281402913e-06,
"loss": 2.4282,
"step": 298500
},
{
"epoch": 7.08,
"learning_rate": 1.3780345360987468e-06,
"loss": 2.4311,
"step": 299000
},
{
"epoch": 7.09,
"learning_rate": 1.3148972440572025e-06,
"loss": 2.4471,
"step": 299500
},
{
"epoch": 7.1,
"learning_rate": 1.251759952015658e-06,
"loss": 2.433,
"step": 300000
},
{
"epoch": 7.1,
"eval_loss": 3.150994062423706,
"eval_runtime": 112.8159,
"eval_samples_per_second": 166.395,
"eval_steps_per_second": 20.804,
"step": 300000
},
{
"epoch": 7.11,
"learning_rate": 1.1886226599741138e-06,
"loss": 2.4182,
"step": 300500
},
{
"epoch": 7.13,
"learning_rate": 1.1254853679325695e-06,
"loss": 2.4228,
"step": 301000
},
{
"epoch": 7.14,
"learning_rate": 1.062348075891025e-06,
"loss": 2.4385,
"step": 301500
},
{
"epoch": 7.15,
"learning_rate": 9.992107838494808e-07,
"loss": 2.4361,
"step": 302000
},
{
"epoch": 7.16,
"learning_rate": 9.360734918079364e-07,
"loss": 2.43,
"step": 302500
},
{
"epoch": 7.17,
"learning_rate": 8.729361997663921e-07,
"loss": 2.4245,
"step": 303000
},
{
"epoch": 7.19,
"learning_rate": 8.097989077248477e-07,
"loss": 2.4383,
"step": 303500
},
{
"epoch": 7.2,
"learning_rate": 7.466616156833035e-07,
"loss": 2.4207,
"step": 304000
},
{
"epoch": 7.21,
"learning_rate": 6.835243236417591e-07,
"loss": 2.4286,
"step": 304500
},
{
"epoch": 7.22,
"learning_rate": 6.203870316002147e-07,
"loss": 2.4143,
"step": 305000
},
{
"epoch": 7.23,
"learning_rate": 5.572497395586704e-07,
"loss": 2.4354,
"step": 305500
},
{
"epoch": 7.25,
"learning_rate": 4.94112447517126e-07,
"loss": 2.4345,
"step": 306000
},
{
"epoch": 7.26,
"learning_rate": 4.309751554755817e-07,
"loss": 2.4294,
"step": 306500
},
{
"epoch": 7.27,
"learning_rate": 3.678378634340374e-07,
"loss": 2.4442,
"step": 307000
},
{
"epoch": 7.28,
"learning_rate": 3.04700571392493e-07,
"loss": 2.4416,
"step": 307500
},
{
"epoch": 7.29,
"learning_rate": 2.4156327935094866e-07,
"loss": 2.4323,
"step": 308000
},
{
"epoch": 7.3,
"learning_rate": 1.7842598730940432e-07,
"loss": 2.4233,
"step": 308500
},
{
"epoch": 7.32,
"learning_rate": 1.1528869526785997e-07,
"loss": 2.4391,
"step": 309000
},
{
"epoch": 7.33,
"learning_rate": 5.2151403226315624e-08,
"loss": 2.442,
"step": 309500
},
{
"epoch": 7.34,
"learning_rate": 0.0,
"loss": 2.4491,
"step": 310000
},
{
"epoch": 7.34,
"eval_loss": 3.1522228717803955,
"eval_runtime": 112.8215,
"eval_samples_per_second": 166.387,
"eval_steps_per_second": 20.803,
"step": 310000
},
{
"epoch": 7.35,
"learning_rate": 0.0,
"loss": 2.4227,
"step": 310500
},
{
"epoch": 7.36,
"learning_rate": 0.0,
"loss": 2.4456,
"step": 311000
},
{
"epoch": 7.38,
"learning_rate": 0.0,
"loss": 2.4356,
"step": 311500
},
{
"epoch": 7.39,
"learning_rate": 0.0,
"loss": 2.418,
"step": 312000
},
{
"epoch": 7.4,
"learning_rate": 0.0,
"loss": 2.4147,
"step": 312500
},
{
"epoch": 7.41,
"learning_rate": 0.0,
"loss": 2.4251,
"step": 313000
},
{
"epoch": 7.42,
"learning_rate": 0.0,
"loss": 2.4257,
"step": 313500
},
{
"epoch": 7.43,
"learning_rate": 0.0,
"loss": 2.4262,
"step": 314000
},
{
"epoch": 7.45,
"learning_rate": 0.0,
"loss": 2.4455,
"step": 314500
},
{
"epoch": 7.46,
"learning_rate": 0.0,
"loss": 2.4248,
"step": 315000
},
{
"epoch": 7.47,
"learning_rate": 0.0,
"loss": 2.4259,
"step": 315500
},
{
"epoch": 7.48,
"learning_rate": 0.0,
"loss": 2.4316,
"step": 316000
},
{
"epoch": 7.49,
"learning_rate": 0.0,
"loss": 2.4504,
"step": 316500
},
{
"epoch": 7.51,
"learning_rate": 0.0,
"loss": 2.4376,
"step": 317000
},
{
"epoch": 7.52,
"learning_rate": 0.0,
"loss": 2.4344,
"step": 317500
},
{
"epoch": 7.53,
"learning_rate": 0.0,
"loss": 2.4206,
"step": 318000
},
{
"epoch": 7.54,
"learning_rate": 0.0,
"loss": 2.4362,
"step": 318500
},
{
"epoch": 7.55,
"learning_rate": 0.0,
"loss": 2.4301,
"step": 319000
},
{
"epoch": 7.56,
"learning_rate": 0.0,
"loss": 2.4291,
"step": 319500
},
{
"epoch": 7.58,
"learning_rate": 0.0,
"loss": 2.4299,
"step": 320000
},
{
"epoch": 7.58,
"eval_loss": 3.1522228717803955,
"eval_runtime": 112.8702,
"eval_samples_per_second": 166.315,
"eval_steps_per_second": 20.794,
"step": 320000
},
{
"epoch": 7.59,
"learning_rate": 0.0,
"loss": 2.4285,
"step": 320500
},
{
"epoch": 7.6,
"learning_rate": 0.0,
"loss": 2.4267,
"step": 321000
},
{
"epoch": 7.61,
"learning_rate": 0.0,
"loss": 2.4389,
"step": 321500
},
{
"epoch": 7.62,
"learning_rate": 0.0,
"loss": 2.4277,
"step": 322000
},
{
"epoch": 7.64,
"learning_rate": 0.0,
"loss": 2.4349,
"step": 322500
},
{
"epoch": 7.65,
"learning_rate": 0.0,
"loss": 2.4376,
"step": 323000
},
{
"epoch": 7.66,
"learning_rate": 0.0,
"loss": 2.4453,
"step": 323500
},
{
"epoch": 7.67,
"learning_rate": 0.0,
"loss": 2.4331,
"step": 324000
},
{
"epoch": 7.68,
"learning_rate": 0.0,
"loss": 2.4418,
"step": 324500
},
{
"epoch": 7.69,
"learning_rate": 0.0,
"loss": 2.4342,
"step": 325000
},
{
"epoch": 7.71,
"learning_rate": 0.0,
"loss": 2.4216,
"step": 325500
},
{
"epoch": 7.72,
"learning_rate": 0.0,
"loss": 2.4335,
"step": 326000
},
{
"epoch": 7.73,
"learning_rate": 0.0,
"loss": 2.4472,
"step": 326500
},
{
"epoch": 7.74,
"learning_rate": 0.0,
"loss": 2.4415,
"step": 327000
},
{
"epoch": 7.75,
"learning_rate": 0.0,
"loss": 2.4462,
"step": 327500
},
{
"epoch": 7.77,
"learning_rate": 0.0,
"loss": 2.4519,
"step": 328000
},
{
"epoch": 7.78,
"learning_rate": 0.0,
"loss": 2.3932,
"step": 328500
},
{
"epoch": 7.79,
"learning_rate": 0.0,
"loss": 2.425,
"step": 329000
},
{
"epoch": 7.8,
"learning_rate": 0.0,
"loss": 2.4297,
"step": 329500
},
{
"epoch": 7.81,
"learning_rate": 0.0,
"loss": 2.4363,
"step": 330000
},
{
"epoch": 7.81,
"eval_loss": 3.1522228717803955,
"eval_runtime": 112.8083,
"eval_samples_per_second": 166.406,
"eval_steps_per_second": 20.805,
"step": 330000
},
{
"epoch": 7.83,
"learning_rate": 0.0,
"loss": 2.4532,
"step": 330500
},
{
"epoch": 7.84,
"learning_rate": 0.0,
"loss": 2.4236,
"step": 331000
},
{
"epoch": 7.85,
"learning_rate": 0.0,
"loss": 2.4411,
"step": 331500
},
{
"epoch": 7.86,
"learning_rate": 0.0,
"loss": 2.4269,
"step": 332000
},
{
"epoch": 7.87,
"learning_rate": 0.0,
"loss": 2.4323,
"step": 332500
},
{
"epoch": 7.88,
"learning_rate": 0.0,
"loss": 2.4343,
"step": 333000
},
{
"epoch": 7.9,
"learning_rate": 0.0,
"loss": 2.4647,
"step": 333500
},
{
"epoch": 7.91,
"learning_rate": 0.0,
"loss": 2.4331,
"step": 334000
},
{
"epoch": 7.92,
"learning_rate": 0.0,
"loss": 2.439,
"step": 334500
},
{
"epoch": 7.93,
"learning_rate": 0.0,
"loss": 2.4262,
"step": 335000
},
{
"epoch": 7.94,
"learning_rate": 0.0,
"loss": 2.4369,
"step": 335500
},
{
"epoch": 7.96,
"learning_rate": 0.0,
"loss": 2.4286,
"step": 336000
},
{
"epoch": 7.97,
"learning_rate": 0.0,
"loss": 2.4323,
"step": 336500
},
{
"epoch": 7.98,
"learning_rate": 0.0,
"loss": 2.4318,
"step": 337000
},
{
"epoch": 7.99,
"learning_rate": 0.0,
"loss": 2.4301,
"step": 337500
},
{
"epoch": 8.0,
"learning_rate": 0.0,
"loss": 2.436,
"step": 338000
},
{
"epoch": 8.01,
"learning_rate": 0.0,
"loss": 2.4323,
"step": 338500
},
{
"epoch": 8.03,
"learning_rate": 0.0,
"loss": 2.4118,
"step": 339000
},
{
"epoch": 8.04,
"learning_rate": 0.0,
"loss": 2.4001,
"step": 339500
},
{
"epoch": 8.05,
"learning_rate": 0.0,
"loss": 2.4181,
"step": 340000
},
{
"epoch": 8.05,
"eval_loss": 3.1522228717803955,
"eval_runtime": 112.9345,
"eval_samples_per_second": 166.22,
"eval_steps_per_second": 20.782,
"step": 340000
},
{
"epoch": 8.06,
"learning_rate": 0.0,
"loss": 2.4242,
"step": 340500
},
{
"epoch": 8.07,
"learning_rate": 0.0,
"loss": 2.4302,
"step": 341000
},
{
"epoch": 8.09,
"learning_rate": 0.0,
"loss": 2.4193,
"step": 341500
},
{
"epoch": 8.1,
"learning_rate": 0.0,
"loss": 2.4164,
"step": 342000
},
{
"epoch": 8.11,
"learning_rate": 0.0,
"loss": 2.4209,
"step": 342500
},
{
"epoch": 8.12,
"learning_rate": 0.0,
"loss": 2.4416,
"step": 343000
},
{
"epoch": 8.13,
"learning_rate": 0.0,
"loss": 2.4181,
"step": 343500
},
{
"epoch": 8.14,
"learning_rate": 0.0,
"loss": 2.4254,
"step": 344000
},
{
"epoch": 8.16,
"learning_rate": 0.0,
"loss": 2.4127,
"step": 344500
},
{
"epoch": 8.17,
"learning_rate": 0.0,
"loss": 2.4414,
"step": 345000
},
{
"epoch": 8.18,
"learning_rate": 0.0,
"loss": 2.4366,
"step": 345500
},
{
"epoch": 8.19,
"learning_rate": 0.0,
"loss": 2.433,
"step": 346000
},
{
"epoch": 8.2,
"learning_rate": 0.0,
"loss": 2.4206,
"step": 346500
},
{
"epoch": 8.22,
"learning_rate": 0.0,
"loss": 2.4424,
"step": 347000
},
{
"epoch": 8.23,
"learning_rate": 0.0,
"loss": 2.4264,
"step": 347500
},
{
"epoch": 8.24,
"learning_rate": 0.0,
"loss": 2.433,
"step": 348000
},
{
"epoch": 8.25,
"learning_rate": 0.0,
"loss": 2.4261,
"step": 348500
},
{
"epoch": 8.26,
"learning_rate": 0.0,
"loss": 2.4225,
"step": 349000
},
{
"epoch": 8.27,
"learning_rate": 0.0,
"loss": 2.4319,
"step": 349500
},
{
"epoch": 8.29,
"learning_rate": 0.0,
"loss": 2.4333,
"step": 350000
},
{
"epoch": 8.29,
"eval_loss": 3.1522228717803955,
"eval_runtime": 113.0119,
"eval_samples_per_second": 166.106,
"eval_steps_per_second": 20.768,
"step": 350000
}
],
"max_steps": 633540,
"num_train_epochs": 15,
"total_flos": 7.3929090776832e+16,
"trial_name": null,
"trial_params": null
}